Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages, covering a population of over 160 million speakers of: Amharic, Bambara, Igbo, Sepedi (Northern Sotho), Shona, Sesotho (Southern Sotho), Setswana, and Tsonga. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology. Using the translated benchmarks, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages. Finally, using results from over 400 fine-tuned models, we explore several methods to reduce the LLM performance gap, including high-quality dataset fine-tuning (using an LLM-as-an-Annotator), cross-lingual transfer, and cultural appropriateness adjustments. Key findings include average mono-lingual improvements of 5.6% with fine-tuning (with 5.4% average mono-lingual improvements when using high-quality data over low-quality data), 2.9% average gains from cross-lingual transfer, and a 3.0% out-of-the-box performance boost on culturally appropriate questions. The publicly available benchmarks, translations, and code from this study support further research and development aimed at creating more inclusive and effective language technologies.

Mechanical Ventilation (MV) is a critical life-support intervention in intensive care units (ICUs). However, optimal ventilator settings are challenging to determine because of the complexity of balancing patient-specific physiological needs with the risks of adverse outcomes that impact morbidity, mortality, and healthcare costs. This study introduces ConformalDQN, a novel distribution-free conformal deep Q-learning approach for optimizing mechanical ventilation in intensive care units. By integrating conformal prediction with deep reinforcement learning, our method provides reliable uncertainty quantification, addressing the challenges of Q-value overestimation and out-of-distribution actions in offline settings. We trained and evaluated our model using ICU patient records from the MIMIC-IV database. ConformalDQN extends the Double DQN architecture with a conformal predictor and employs a composite loss function that balances Q-learning with well-calibrated probability estimation. This enables uncertainty-aware action selection, allowing the model to avoid potentially harmful actions in unfamiliar states and handle distribution shifts by being more conservative in out-of-distribution scenarios. Evaluation against baseline models, including physician policies, policy constraint methods, and behavior cloning, demonstrates that ConformalDQN consistently makes recommendations within clinically safe and relevant ranges, outperforming other methods by increasing the 90-day survival rate. Notably, our approach provides an interpretable measure of confidence in its decisions, which is crucial for clinical adoption and potential human-in-the-loop implementations.

Reza Khanmohammadi, Erfan Miahi, Mehrsa Mardikoraem, Simerjot Kaur, Ivan Brugere, Charese Smiley, Kundan S Thind, Mohammad M. Ghassemi. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Surface Electromyography (sEMG) is a non-invasive signal that is used in the recognition of hand movement patterns, the diagnosis of diseases, and the robust control of prostheses. Despite the remarkable success of recent end-to-end Deep Learning approaches, they are still limited by the need for large amounts of labeled data. To alleviate the requirement for big data, we propose utilizing a feature-imitating network (FIN) for closed-form temporal feature learning over a 300ms signal window on Ninapro DB2, and applying it to the task of 17 hand movement recognition. We implement a lightweight LSTM-FIN network to imitate four standard temporal features (entropy, root mean square, variance, simple square integral). We observed that the LSTM-FIN network can achieve up to 99% R2 accuracy in feature reconstruction and 80% accuracy in hand movement recognition. Our results also showed that the model can be robustly applied for both within- and cross-subject movement recognition, as well as simulated low-latency environments. Overall, our work demonstrates the potential of the FIN modeling paradigm in data-scarce scenarios for sEMG signal processing.

Vision Transformers (ViTs) have shown promise in medical image semantic segmentation (MISS) by capturing longrange correlations. However, ViTs often struggle to model local spatial information effectively, which is essential for accurately segmenting fine anatomical details, particularly when applied to small datasets without extensive pre-training. We introduce Gabor and Laplacian of Gaussian Convolutional Swin Network (GLoG-CSUnet), a novel architecture enhancing Transformer-based models by incorporating learnable radiomic features. This approach integrates dynamically adaptive Gabor and Laplacian of Gaussian (LoG) filters to capture texture, edge, and boundary information, enhancing the feature representation processed by the Transformer model. Our method uniquely combines the longrange dependency modeling of Transformers with the texture analysis capabilities of Gabor and LoG features. Evaluated on the Synapse multi-organ and ACDC cardiac segmentation datasets, GLoG-CSUnet demonstrates significant improvements over stateof-the-art models, achieving a 1.14% increase in Dice score for Synapse and 0.99% for ACDC, with minimal computational overhead (only 15 and 30 additional parameters, respectively). GLoG-CSUnet’s flexible design allows integration with various base models, offering a promising approach for incorporating radiomics-inspired feature extraction in Transformer architectures for medical image analysis. The code implementation is available on GitHub at: https://github.com/HAAIL/GLoGCSUnet.

The relationship between scientific innovation in biomedical sciences and its impact on industrial activities is a complex and dynamic process. This article investigates the relationship between science and industrial innovation, focusing on how the historical impact and content of scientific paper abstracts are associated with future funding and innovation grant application content for small businesses. The research incorporates bibliometric analyses along with small business innovation research (SBIR) data to yield a holistic view of the science-industry interface. We quantify the temporal effects and impact latency of scientific advancements on industrial activity across 10873 topics and take into account their taxonomic relationships, spanning from 2010 to 2021. We find that the impact of scientific advances on industrial projects across different thematic depths consistently exhibitedp-values less than 0.05, underscoring the significant predictive power of contemporary scientific activities on future industrial projects. Further, we demonstrate that the semantic contents of scientific paper abstracts within a topic are associated with future industrial project description text embeddings. The frequency analysis reveals that various scientific activities significantly inform future industrial project funding across varying depths of MeSH topic categorization, highlighting the significant role of science in steering industrial innovation. This study demonstrates that the impact of scientific research on industrial innovation extends beyond the mere volume of scientific output, but is greatly influenced by its impact, the broader themes it advances, and the meaningful narratives it presents.

We introduce a novel approach to neural learning: the Feature-Imitating-Network (FIN). A FIN is a neural network with weights that are initialized to reliably approximate one or more closed-form statistical features, such as Shannon’s entropy. In this paper, we demonstrate that FINs (and FIN ensembles) provide best-in-class performance for a variety of downstream signal processing and inference tasks, while using less data and requiring less fine-tuning compared to other networks of similar (or even greater) representational power. We conclude that FINs can help bridge the gap between domain experts and machine learning practitioners by enabling re-searchers to harness insights from feature-engineering to enhance the performance of contemporary representation learning approaches.

Bias can have devastating outcomes on everyday life, and may manifest in subtle preferences for particular attributes (age, gender, ethnicity, profession). Understanding bias is complex, but first requires identifying the variety and interplay of individual preferences. In this study, we deployed a sociotechnical, web-based human-subject experiment to quantify individual preferences in the context of selecting an advisor to successfully pitch a government-expense. We utilized conjoint analysis to rank the preferences of 722 U.S. based subjects, and observed that their ideal advisor was White, middle-aged, and of either a government or STEM-related profession (0.68 AUROC, p < 0.05). The results motivate the simultaneous measurement of preferences as a strategy to offset preferences that may yield negative consequences (e.g. prejudice, disenfranchisement) in contexts where social interests are being represented.

Electrode “pop” artifacts originate from the spontaneous loss of connectivity between a surface and an electrode. Electroencephalography (EEG) uses a dense array of electrodes, hence popped segments are among the most pervasive type of artifact seen during the collection of EEG data. In many cases, the continuity of EEG data is critical for downstream applications (e.g. brain machine interface) and requires that popped segments be accurately interpolated. In this paper we frame the interpolation problem as a self-learning task using a deep encoder-decoder network. We compare our approach against contemporary interpolation methods on a publicly available EEG data set. Our approach exhibited a minimum of ~15% improvement over contemporary approaches when tested on subjects and tasks not used during model training. We demonstrate how our model's performance can be enhanced further on novel subjects and tasks using transfer learning. All code and data associated with this study is open-source to enable ease of extension and practical use. To our knowledge, this work is the first solution to the EEG interpolation problem that uses deep learning.

In this paper, we present SPread, an automated financial metric extraction and spreading tool from earnings reports. The tool is created in a document-agnostic fashion, and uses an interpolation of tagging methods to capture arbitrarily complicated expressions. SPread can handle single-line items as well as metrics broken down into sub-items. A validation layer further improves the performance of upstream modules and enables the tool to reach an F1 performance of more than 87% for metrics expressed in tabular format, and 76% for metrics in free-form text. The results are displayed to end-users in an interactive web interface, which allows them to locate, compare, validate, adjust, and export the values.

Inferring the latent emotive content of a narrative requires consideration of para-linguistic cues (e.g. pitch), linguistic content (e.g. vocabulary) and the physiological state of the narrator (e.g. heart-rate). In this study we utilized a combination of auditory, text, and physiological signals to predict the mood (happy or sad) of 31 narrations from subjects engaged in personal story-telling. We extracted 386 audio and 222 physiological features (using the Samsung Simband) from the data. A subset of 4 audio, 1 text, and 5 physiologic features were identified using Sequential Forward Selection (SFS) for inclusion in a Neural Network (NN). These features included subject movement, cardiovascular activity, energy in speech, probability of voicing, and linguistic sentiment (i.e. negative or positive). We explored the effects of introducing our selected features at various layers of the NN and found that the location of these features in the network topology had a significant impact on model performance. To ensure the real-time utility of the model, classification was performed over 5 second intervals. We evaluated our model’s performance using leave-one-subject-out crossvalidation and compared the performance to 20 baseline models and a NN with all features included in the input layer.

Clinical researchers, historians, educators and field researchers alike still regularly capture data on paper spreadsheets. In the case of health care and education, data will often contain sensitive personal information, further complicating the process of transcribing paper-based archives into digital form. In this work, we describe a tool that utilizes machine learning and crowd intelligence to automatically transcribe images of paper-based spreadsheets into electronic form while protecting sensitive personal information. Our solution consists of four high-level stages: (1) the extraction of cell-level images from the spreadsheet grid, (2) machine recognition of digits within the cells, (3) human transcription of cell contents that the machine was uncertain of and (4) feedback of human transcription results to the machine to improve future classification performance. We test the algorithm on a novel data-set of 135 heterogeneous clinical flow-sheet images collected from the Massachusetts General Hospital (MGH), 2 hand-drawn spreadsheets, one chalk-board drawing, and one printed table. we demonstrate that our algorithm provides a generalized solution for spreadsheet transcription that maintains privacy, is up to 10 times faster and twice as cost effective than existing alternatives. Our work is valuable both as a tool and as a starting point for the development of better algorithms.

Two of the major problems in social media message classification are the data sparseness issue and the high degree of lexical variation. Paraphrases, or synonyms, are alternative ways of expressing the same meaning using different lexical variations. In this study, we try to use paraphrases to improve tweet topic classification performance. We explored two approaches to generating paraphrases, WordNet, which is a lexical database grouping English words into sets of synonyms, and word embeddings, which are learned from millions of tweets and billions of words. Our experiment shows that using paraphrases can improve the topic classification task, and the word embedding approach outperforms the WordNet method. To our knowledge, this is the first study exploiting paraphrases for tweet classification.

Clinical data management systems typically provide caregiver teams with useful information, derived from large, sometimes highly heterogeneous, data sources that are often changing dynamically. Over the last decade there has been a significant surge in interest in using these data sources, from simply re-using the standard clinical databases for event prediction or decision support, to including dynamic and patient-specific information into clinical monitoring and prediction problems. However, in most cases, commercial clinical databases have been designed to document clinical activity for reporting, liability and billing reasons, rather than for developing new algorithms. With increasing excitement surrounding "secondary use of medical records" and "Big Data" analytics, it is important to understand the limitations of current databases and what needs to change in order to enter an era of "precision medicine." This review article covers many of the issues involved in the collection and preprocessing of critical care data. The three challenges in critical care are considered: compartmentalization, corruption, and complexity. A range of applications addressing these issues are covered, including the modernization of static acuity scoring; on-line patient tracking; personalized prediction and risk assessment; artifact detection; state estimation; and incorporation of multimodal data sources such as genomic and free text data.

Robust navigation and mining of physiologic time series databases often requires finding similar temporal patterns of physiological responses. Detection of these complex physiological patterns not only enables demarcation of important clinical events but can also elucidate hidden dynamical structures that may be suggestive of disease processes. Some specific examples where this physiological signal search may be useful include real-time detection of cardiac arrhythmias, sleep staging or detection of seizure onset. In all these cases, being able to identify a cohort of patients who exhibit similar physiological dynamics could be useful in prognosis and informing treatment strategies. However, pattern recognition for physiological time series is complicated by changes between operating regimes and measurement artifacts. Here we briefly describe an approach we have developed for distributed identification of dynamical patterns in physiological time series using a switching linear dynamical system (SLDS). We present a fast and memory-efficient algorithm for learning and retrieval of phenotypic dynamics in large clinical time series databases. Through simulation we show that the proposed algorithm is at least an order of magnitude faster that the state of the art, and provide encouraging preliminary results based on real recordings of vital sign time series from the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC-II) database.

Analyzing Biomedical Big Data (BBD) is computationally expensive due to high dimensionality and large data volume. Performance and scalability issues of traditional database management systems (DBMS) often limit the usage of more sophisticated and complex data queries and analytic models. Moreover, in the conventional setting, data management and analysis use separate software platforms. Exporting and importing large amounts of data across platforms require a significant amount of computational and I/O resources, as well as potentially putting sensitive data at a security risk. In this tutorial, the participants will learn the difference between in-memory DBMS and traditional DBMS through hands-on exercises using SAP's cloud-based HANA in-memory DBMS in conjunction with the Multi-parameter Intelligent Monitoring in Intensive Care (MIMIC) dataset. MIMIC is an open-access critical care EHR archive (over 4TB in size) and consists of structured, unstructured and waveform data. Furthermore, this tutorial will seek to educate the participants on how a combination of dynamic querying, and in-memory DBMS may enhance the management and analysis of complex clinical data.